INDEX
    Explanations

    properties and features related to real estate developments

    New Auto-Interp
    Negative Logits
    wa
    -0.16
    mac
    -0.16
    atters
    -0.15
    ifter
    -0.15
     mac
    -0.14
    ync
    -0.14
     training
    -0.14
     moss
    -0.14
     Moj
    -0.14
     |=
    -0.14
    POSITIVE LOGITS
    flen
    0.15
     Std
    0.15
    uct
    0.14
     eldre
    0.14
    unate
    0.14
    cling
    0.14
    ahat
    0.14
     !:
    0.14
    æı
    0.13
    ripp
    0.13
    Act Density 0.158%

    No Known Activations